Giters

yiqun-wang / HFS

HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (NeurIPS 2022)

Home Page:https://arxiv.org/abs/2206.07850

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Intensive Memory Usage

yyeboah opened this issue · comments

commented

Thanks for open-sourcing your work with the greater community. The recovered high-frequency details are indeed noticeable, albeit with extra training latency. One other issue I'd like to highlight, and hopefully get your input on is the GPU memory overhead which seems to scale rather intensely with image resolution and number.

Is there a way to mitigate this memory overhead for larger datasets without trading off too much of accuracy? The rays/batch size does not seem to help in this regard.